Rémi
@remilouf.bsky.social
CEO & co-founder at .txt. I wander.
Pinned
Rémi
@remilouf.bsky.social
· Nov 20
dottxt - make ai speak computer
dottxt.co
👋 New followers
I’m Rémi, co-founder and CEO of @dottxtai.bsky.social. We do structured generation with LLM, which means we are able to enforce constraints on the output (regex, JSON Schema, Grammar) during inference time. It’s very cool.
dottxt.co
I’m Rémi, co-founder and CEO of @dottxtai.bsky.social. We do structured generation with LLM, which means we are able to enforce constraints on the output (regex, JSON Schema, Grammar) during inference time. It’s very cool.
dottxt.co
Reposted by Rémi
We changed the way we handle multimodal inputs in Outlines.
Most libraries will give the prompt a special role, separate it from the other inputs. We don’t anymore.
Most libraries will give the prompt a special role, separate it from the other inputs. We don’t anymore.
July 13, 2025 at 5:11 PM
We changed the way we handle multimodal inputs in Outlines.
Most libraries will give the prompt a special role, separate it from the other inputs. We don’t anymore.
Most libraries will give the prompt a special role, separate it from the other inputs. We don’t anymore.
Reposted by Rémi
📝 I have been meaning to write this for a while now, but after reading @remilouf.bsky.social's post on the potential of structured generation for LLMs and a post on SerDes debt deriving from Pydantic usage, I decided I should not wait any longer. So here is my new blog post:
July 12, 2025 at 4:57 PM
📝 I have been meaning to write this for a while now, but after reading @remilouf.bsky.social's post on the potential of structured generation for LLMs and a post on SerDes debt deriving from Pydantic usage, I decided I should not wait any longer. So here is my new blog post:
Reposted by Rémi
🦀 Do you like Rust?
🇫🇷 Do you like Paris?
Then you'll love the conference, Rust In Paris, that my colleague Yvan Sraka is delivering his talk, Beyond Procedural Macros: A Trait-Based Framework for Bindgen, at next month!
www.rustinparis.com
🇫🇷 Do you like Paris?
Then you'll love the conference, Rust In Paris, that my colleague Yvan Sraka is delivering his talk, Beyond Procedural Macros: A Trait-Based Framework for Bindgen, at next month!
www.rustinparis.com
February 19, 2025 at 3:54 PM
🦀 Do you like Rust?
🇫🇷 Do you like Paris?
Then you'll love the conference, Rust In Paris, that my colleague Yvan Sraka is delivering his talk, Beyond Procedural Macros: A Trait-Based Framework for Bindgen, at next month!
www.rustinparis.com
🇫🇷 Do you like Paris?
Then you'll love the conference, Rust In Paris, that my colleague Yvan Sraka is delivering his talk, Beyond Procedural Macros: A Trait-Based Framework for Bindgen, at next month!
www.rustinparis.com
Reposted by Rémi
This was absolutely my favorite talk from today! Love it / scared of it
I'll be presenting the self-expanding knowledge graph at an upcoming talk and it is easily my favorite demo
Signup if you're in San Francisco: lu.ma/2jacrv79
Signup if you're in San Francisco: lu.ma/2jacrv79
January 24, 2025 at 4:36 AM
This was absolutely my favorite talk from today! Love it / scared of it
Reposted by Rémi
Outlines 0.1.9 release is out! Small release, but some highlights:
- First contribution by @chicham!
- You can now use enums in outlines.generate.choice
- Compilation time improvements.
- Using the rust-native JSON-schema to regex, rather than the Python implementation
- First contribution by @chicham!
- You can now use enums in outlines.generate.choice
- Compilation time improvements.
- Using the rust-native JSON-schema to regex, rather than the Python implementation
December 11, 2024 at 12:17 PM
Outlines 0.1.9 release is out! Small release, but some highlights:
- First contribution by @chicham!
- You can now use enums in outlines.generate.choice
- Compilation time improvements.
- Using the rust-native JSON-schema to regex, rather than the Python implementation
- First contribution by @chicham!
- You can now use enums in outlines.generate.choice
- Compilation time improvements.
- Using the rust-native JSON-schema to regex, rather than the Python implementation
Reposted by Rémi
This is actually good to show skeptics of structured generation @dottxtai.bsky.social. Demonstrates very clearly that you can stop the model from fighting the constraints by telling it how it’s constrained, even if those constraints might seem absurd (like only using words from the King James Bible)
December 7, 2024 at 3:58 AM
This is actually good to show skeptics of structured generation @dottxtai.bsky.social. Demonstrates very clearly that you can stop the model from fighting the constraints by telling it how it’s constrained, even if those constraints might seem absurd (like only using words from the King James Bible)
HF has done, and keeps doing, a lot of good in the AI ecosystem. I’ll die on this hill.
November 28, 2024 at 1:45 PM
HF has done, and keeps doing, a lot of good in the AI ecosystem. I’ll die on this hill.
More insults under an apology post on Bluesky than under any outrageous post on Twitter. Be the change you want to see in the world or something like that.
November 28, 2024 at 9:30 AM
More insults under an apology post on Bluesky than under any outrageous post on Twitter. Be the change you want to see in the world or something like that.
Reposted by Rémi
Check out our new YouTube video. We're trying out kind of an interview format, so let me know if you love/hate this
New video! @cameron.pfiffer.org talks to our computational linguist Daniel Quernheim.
Learn what context free grammars are, and how to make JSON where every string has to start with the letter A.
youtu.be/rMHdpo_D9m0?...
Learn what context free grammars are, and how to make JSON where every string has to start with the letter A.
youtu.be/rMHdpo_D9m0?...
Understanding Context-Free Grammars: An Interview with .txt's Daniel Quernheim!
YouTube video by dottxt
youtu.be
November 26, 2024 at 4:47 PM
Check out our new YouTube video. We're trying out kind of an interview format, so let me know if you love/hate this
Looking at the comments of this one, I think this is actually the Bad Place
Releasing: a dataset of two million Bluesky posts.
This dataset has been collected using Bluesky's API, and I hope it will be useful for all the researchers out there!
This dataset has been collected using Bluesky's API, and I hope it will be useful for all the researchers out there!
November 28, 2024 at 12:27 AM
Looking at the comments of this one, I think this is actually the Bad Place
The comments on this are unnecessarily hateful. I thought this place was better.
First dataset for the new @huggingface.bsky.social @bsky.app community organisation: one-million-bluesky-posts 🦋
📊 1M public posts from Bluesky's firehose API
🔍 Includes text, metadata, and language predictions
🔬 Perfect to experiment with using ML for Bluesky 🤗
huggingface.co/datasets/blu...
📊 1M public posts from Bluesky's firehose API
🔍 Includes text, metadata, and language predictions
🔬 Perfect to experiment with using ML for Bluesky 🤗
huggingface.co/datasets/blu...
bluesky-community/one-million-bluesky-posts · Datasets at Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
November 27, 2024 at 7:06 PM
The comments on this are unnecessarily hateful. I thought this place was better.
Give @dottxtai.bsky.social a follow for quality structured generation content!
November 24, 2024 at 4:07 PM
Give @dottxtai.bsky.social a follow for quality structured generation content!
Reposted by Rémi
A new paper, "Let Me Speak Freely" has been spreading rumors that structured generation hurts LLM evaluation performance.
Well, we've taken a look and found serious issue in this paper, and shown, once again, that structured generation *improves* evaluation performance!
Well, we've taken a look and found serious issue in this paper, and shown, once again, that structured generation *improves* evaluation performance!
November 21, 2024 at 6:33 PM
A new paper, "Let Me Speak Freely" has been spreading rumors that structured generation hurts LLM evaluation performance.
Well, we've taken a look and found serious issue in this paper, and shown, once again, that structured generation *improves* evaluation performance!
Well, we've taken a look and found serious issue in this paper, and shown, once again, that structured generation *improves* evaluation performance!
The "Let Me Speak Freely" got way too much traction too easily, despite a few serious issues.
Well aware of Brandolini's law we published a thorough rebuttal of the main conclusion, highlighted the key methodological flaws and taught a few things in the process.
Hope you enjoy it!
Well aware of Brandolini's law we published a thorough rebuttal of the main conclusion, highlighted the key methodological flaws and taught a few things in the process.
Hope you enjoy it!
A new paper, "Let Me Speak Freely" has been spreading rumors that structured generation hurts LLM evaluation performance.
Well, we've taken a look and found serious issue in this paper, and shown, once again, that structured generation *improves* evaluation performance!
Well, we've taken a look and found serious issue in this paper, and shown, once again, that structured generation *improves* evaluation performance!
November 22, 2024 at 6:55 AM
The "Let Me Speak Freely" got way too much traction too easily, despite a few serious issues.
Well aware of Brandolini's law we published a thorough rebuttal of the main conclusion, highlighted the key methodological flaws and taught a few things in the process.
Hope you enjoy it!
Well aware of Brandolini's law we published a thorough rebuttal of the main conclusion, highlighted the key methodological flaws and taught a few things in the process.
Hope you enjoy it!
Reposted by Rémi
Our new blog post is out!
@willkurt.bsky.social provides a rebuttal for a reasonably well known paper which concluded that structured generation with LLMs always resulted in worse performance.
We do not find the same thing.
blog.dottxt.co/say-what-you...
@willkurt.bsky.social provides a rebuttal for a reasonably well known paper which concluded that structured generation with LLMs always resulted in worse performance.
We do not find the same thing.
blog.dottxt.co/say-what-you...
November 21, 2024 at 6:23 PM
Our new blog post is out!
@willkurt.bsky.social provides a rebuttal for a reasonably well known paper which concluded that structured generation with LLMs always resulted in worse performance.
We do not find the same thing.
blog.dottxt.co/say-what-you...
@willkurt.bsky.social provides a rebuttal for a reasonably well known paper which concluded that structured generation with LLMs always resulted in worse performance.
We do not find the same thing.
blog.dottxt.co/say-what-you...
Reposted by Rémi
Build an AI receipt scanner with vision language models!
YouTube video by dottxt
youtu.be
November 20, 2024 at 5:19 PM
What’s the best LLM observability tool today?
November 20, 2024 at 8:05 PM
What’s the best LLM observability tool today?
👋 New followers
I’m Rémi, co-founder and CEO of @dottxtai.bsky.social. We do structured generation with LLM, which means we are able to enforce constraints on the output (regex, JSON Schema, Grammar) during inference time. It’s very cool.
dottxt.co
I’m Rémi, co-founder and CEO of @dottxtai.bsky.social. We do structured generation with LLM, which means we are able to enforce constraints on the output (regex, JSON Schema, Grammar) during inference time. It’s very cool.
dottxt.co
dottxt - make ai speak computer
dottxt.co
November 20, 2024 at 8:07 AM
👋 New followers
I’m Rémi, co-founder and CEO of @dottxtai.bsky.social. We do structured generation with LLM, which means we are able to enforce constraints on the output (regex, JSON Schema, Grammar) during inference time. It’s very cool.
dottxt.co
I’m Rémi, co-founder and CEO of @dottxtai.bsky.social. We do structured generation with LLM, which means we are able to enforce constraints on the output (regex, JSON Schema, Grammar) during inference time. It’s very cool.
dottxt.co
I wake up every day with 100 new followers now. The Starter Packs were a brilliant idea ✨
November 20, 2024 at 8:03 AM
I wake up every day with 100 new followers now. The Starter Packs were a brilliant idea ✨
Reposted by Rémi
Hello Bluesky! We're here now. Wonderful to be in the Good Place.
We'll be posting demos, interesting tidbits, and boosting cool AI stuff on here.
dottxt.co
We'll be posting demos, interesting tidbits, and boosting cool AI stuff on here.
dottxt.co
dottxt - make ai speak computer
dottxt.co
November 19, 2024 at 12:42 AM
Hello Bluesky! We're here now. Wonderful to be in the Good Place.
We'll be posting demos, interesting tidbits, and boosting cool AI stuff on here.
dottxt.co
We'll be posting demos, interesting tidbits, and boosting cool AI stuff on here.
dottxt.co
Reposted by Rémi
(Reposting from X)
I did a tiny side project: a program that automatically generates a properly formatted .ics file from a text description (e.g. copy/paste an email) using an LLM, and imports it to your favorite calendar app!
Structured generation is cool -- shoutout @remilouf.bsky.social and .txt
I did a tiny side project: a program that automatically generates a properly formatted .ics file from a text description (e.g. copy/paste an email) using an LLM, and imports it to your favorite calendar app!
Structured generation is cool -- shoutout @remilouf.bsky.social and .txt
November 11, 2024 at 2:39 PM
(Reposting from X)
I did a tiny side project: a program that automatically generates a properly formatted .ics file from a text description (e.g. copy/paste an email) using an LLM, and imports it to your favorite calendar app!
Structured generation is cool -- shoutout @remilouf.bsky.social and .txt
I did a tiny side project: a program that automatically generates a properly formatted .ics file from a text description (e.g. copy/paste an email) using an LLM, and imports it to your favorite calendar app!
Structured generation is cool -- shoutout @remilouf.bsky.social and .txt
📊 One weird trick to parse earnings reports!
Wall Street analysts HATE this!
Use LLMs to convert messy SEC filings into clean CSV data using structured generation.
The one weird trick? Convert your HTML to markdown + use Outlines.
Link below 👇
Wall Street analysts HATE this!
Use LLMs to convert messy SEC filings into clean CSV data using structured generation.
The one weird trick? Convert your HTML to markdown + use Outlines.
Link below 👇
November 7, 2024 at 9:32 AM
📊 One weird trick to parse earnings reports!
Wall Street analysts HATE this!
Use LLMs to convert messy SEC filings into clean CSV data using structured generation.
The one weird trick? Convert your HTML to markdown + use Outlines.
Link below 👇
Wall Street analysts HATE this!
Use LLMs to convert messy SEC filings into clean CSV data using structured generation.
The one weird trick? Convert your HTML to markdown + use Outlines.
Link below 👇
To celebrate the release of @huggingface.bsky.social’s new SmolLM2 series of models we created a fun demo: the Bunny B1.
The Bunny B1 shows how a small device using a SmolLM2 model + Outlines can consistently map natural language requests to the correct app!
Check it out in this gif!
The Bunny B1 shows how a small device using a SmolLM2 model + Outlines can consistently map natural language requests to the correct app!
Check it out in this gif!
November 5, 2024 at 1:48 PM
To celebrate the release of @huggingface.bsky.social’s new SmolLM2 series of models we created a fun demo: the Bunny B1.
The Bunny B1 shows how a small device using a SmolLM2 model + Outlines can consistently map natural language requests to the correct app!
Check it out in this gif!
The Bunny B1 shows how a small device using a SmolLM2 model + Outlines can consistently map natural language requests to the correct app!
Check it out in this gif!
Reposted by Rémi
Outlines is a great library for structured generation for LLMs/VLMs, which is really helpful for many use cases.
@remilouf.bsky.social and the team are working towards a 1.0.0 release with an API that looks very nice, in my opinion.
@remilouf.bsky.social and the team are working towards a 1.0.0 release with an API that looks very nice, in my opinion.
November 1, 2024 at 9:39 AM
Outlines is a great library for structured generation for LLMs/VLMs, which is really helpful for many use cases.
@remilouf.bsky.social and the team are working towards a 1.0.0 release with an API that looks very nice, in my opinion.
@remilouf.bsky.social and the team are working towards a 1.0.0 release with an API that looks very nice, in my opinion.